Smart technologies for infection control and antimicrobial stewardship in critical care settings: A narrative review

Background: Infection control and antimicrobial stewardship (AMS) remain major challenges in intensive care units (ICUs), driven by delayed diagnostics, extensive empirical antimicrobial use, and escalating antimicrobial resistance. Conventional microbiology-based approaches are often slow and resource-intensive, highlighting the need for adaptive, data-driven solutions. This narrative review synthesises current evidence on the application of smart technologies-artificial intelligence (AI), machine learning (ML), the internet of things (IoT), and telemedicine to enhance infection prevention, early diagnosis, and antimicrobial optimisation in critical care. Methods: A narrative review of 30 peer-reviewed publications was conducted, including original studies, reviews, case studies, and policy reports published between 2020 and 2025. Literature was retrieved from PubMed, Scopus, and Google Scholar, with additional targeted searches focusing on digital stewardship frameworks and ICU-based technological applications. Studies addressing AI, ML, IoT, or telemedicine-enabled infection control or AMS in critical care settings were included. Results: AI and ML models showed strong performance in predicting sepsis, ventilator-associated pneumonia, and multidrug-resistant organism risk, with several studies reporting area under the receiver operating characteristic curve values exceeding 0.80 despite methodological heterogeneity and predominantly retrospective designs . IoT-based systems-such as wearable sensors, smart environmental monitoring, and automated surveillance-enabled real-time physiological and environmental data capture, improving early detection and compliance monitoring. Telemedicine platforms expanded access to infectious disease expertise and AMS services, improving antimicrobial prescribing quality. Digital stewardship tools enhanced prescribing appropriateness and workflow efficiency. Key challenges included data interoperability, cybersecurity, limited model explainability, and scarce multi-centre validation. Conclusion: By facilitating early detection and enhancing antimicrobial decision-making, smart technologies hold great promise for improving AMS in ICUs.